Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to theft or illegally taking something

    oai_token-act-pair · gpt-3.5-turbo

    references to theft, extraction, or seizure of resources or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.68
    tions
    -0.63
    lished
    -0.61
    ĪĴ
    -0.58
    iquette
    -0.58
    lich
    -0.58
    istant
    -0.58
    sted
    -0.57
    ilingual
    -0.56
     Countdown
    -0.56
    POSITIVE LOGITS
     from
    1.16
    from
    1.07
    ById
    1.00
     FROM
    1.00
     cheaply
    0.99
    From
    0.87
    needed
    0.85
     away
    0.85
     From
    0.83
    away
    0.80
    Act Density 0.439%

    No Known Activations